An Intelligent Crime Surveillance Video System For Real-Time Applications
Bibliographic record
Abstract
The increasing frequency of violent incidents underscores the need for advanced real-time surveillance systems. This work proposes an intelligent camera system based on deep learning algorithms for crime monitoring, capable of accurately detecting violence. The system integrates YOLO for high-precision object detection, DeepSort for tracking, OpenPose for pose estimation, and LSTM networks for action Classification. The goal is to create a compact and accurate device that detects hostile activities in real time, triggers an alarm, and stores the offenders’ images in a database. YOLO is used to detect faces in video frames while minimizing false positives, and DeepSort tracks individuals by assigning each a unique ID, enabling continuous surveillance in crowded areas. OpenPose evaluates body positions by identifying key points and their affinities, while an LSTM network classifies actions as violent or non-violent based on posture data. When violence is detected, the system triggers an alarm and captures images, which are securely stored on a Firebase server with timestamps for easy access. This real-time, efficient, and lightweight surveillance system improves crime detection and response across various environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".